INDEX

Explanations

Scottish

np_max-act · gemini-2.0-flash

New Auto-Interp

Configuration

mwhanna/qwen3-4b-transcoders/layer_7.safetensors

Prompts (Dashboard)

16,384 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

163,840

Data Type

float32

Hook Name

blocks.7.mlp.hook_in

Architecture

transcoder

Context Size

8,192

Dataset

monology/pile-uncopyrighted

Embeds

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

--,

-0.28

elle

-0.26

odb

-0.26

ropped

-0.26

erman

-0.24

SEC

-0.24

eled

-0.23

seat

-0.23

 electronics

-0.23

 fetchData

-0.23

POSITIVE LOGITS

å§ĵ

0.30

marshal

0.28

ossa

0.27

åĩłæ¬¡

0.26

ambique

0.26

ç½¢

0.25

çĽĬ

0.25

isodes

0.25

 Gram

0.24

æĢ»éĥ¨

0.24

Activations Density 0.004%

Scottish

No Comments

No Known Activations